Proving the Business Case for the Internet of Things

BeagleBoard development board suits AI applications

Steve Rogerson
September 26, 2019



The BeagleBoard Foundation has introduced the BeagleBone development board targeting artificial intelligence (AI) applications. Built on its open source Linux approach, BeagleBone AI fills the gap between small single board computers and more powerful industrial computers.
 
Leveraging the Texas Instruments Sitara AM5729 processor, developers have access to machine learning capabilities with the ease of the BeagleBone Black header and mechanical compatibility.
 
The board is said to make it easy to explore how AI and machine learning can be used in everyday life. Developers can take advantage of the TI C66x digital-signal-processor cores and embedded-vision-engine cores on the Sitara AM5729 processor.
 
Machine learning is supported by an optimised TI deep learning software framework and pre-installed software tools. Downloading and running the latest examples of edge inference algorithms and applications is only a few clicks away.
 
"This board is the answer to our community's request to see the next major advancement in the BeagleBone family," said Jason Kridner, co-founder of the BeagleBoard Foundation. "Its feature set is jam packed and offers capabilities unparalleled by any other single board computer, open hardware or not."
 
It works with existing BeagleBone cape add-on boards and many available third-party cape add-on boards and enclosures.
 
Features include 1Gbyte RAM and 16Gbyte on-board eMMC flash with a high-speed interface. It has a USB type C interface for power and super-speed dual-role controller, and a USB type A host. Connectivity includes Gigabit Ethernet, 2.4 and 5GHz wifi, and Bluetooth 4.2 and BLE. There is a Micro HDMI video and audio output.
 
The TI Sitara AM5729 processor has a dual 1.5GHz Arm Cortex-A15 microprocessor subsystem, two C66x floating-point VLIW DSPs, four embedded vision engines supported by the TI deep learning software framework library for machine learning, two dual-core programmable real-time unit (PRU) subsystems (four PRUs total) for low latency control and software generated peripherals, two dual Arm Cortex-M4 co-processors for real-time control and subsystem management, an IVA-HD subsystem with support for 4K at 15fps H.264 encode/decode and other codecs at 1080p60, Vivante GC320 2D graphics accelerator, and dual-core Power VR SGX544 3D GPU.
 
"We believe this board will excel in everyday automation in industrial, commercial and home applications," said Christine Long, executive director of the BeagleBoard Foundation. "And at an extremely competitive price point we've made this board available to everyone. It's an industry game changer."